© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47148
    Prev
    Next
    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pari
    -0.09
    raid
    -0.08
    વિ
    -0.08
     Belgium
    -0.07
    μια
    -0.07
    ႀက
    -0.07
     election
    -0.07
     എം
    -0.07
    VE
    -0.07
     /*↵
    -0.07
    POSITIVE LOGITS
     flexibil
    0.08
    /Home
    0.07
    ROLLER
    0.07
    #"
    0.07
    는데
    0.07
     произош
    0.07
    届
    0.07
     sailing
    0.07
     izin
    0.07
    Shelf
    0.07
    Activations Density 0.048%

    No Known Activations